Position control of a planar cable-driven parallel robot using reinforcement learning

Basit Öğe Kaydı
dc.authoriditik, Mehmet/0000-0002-3827-5697
dc.authoridSancak, Caner/0000-0003-0795-0204
dc.authoridyamac, fatma/0000-0001-8672-7427
dc.contributor.authorSancak, Caner
dc.contributor.authorYamac, Fatma
dc.contributor.authorItik, Mehmet
dc.date.accessioned2025-03-17T12:25:55Z
dc.date.available2025-03-17T12:25:55Z
dc.date.issued2022
dc.departmentTarsus Üniversitesi
dc.description.abstractThis study proposes a method based on reinforcement learning (RL) for point-to-point and dynamic reference position tracking control of a planar cable-driven parallel robots, which is a multi-input multi-output system (MIMO). The method eliminates the use of a tension distribution algorithm in controlling the system's dynamics and inherently optimizes the cable tensions based on the reward function during the learning process. The deep deterministic policy gradient algorithm is utilized for training the RL agents in point-to-point and dynamic reference tracking tasks. The performances of the two agents are tested on their specifically trained tasks. Moreover, we also implement the agent trained for point-to-point tasks on the dynamic reference tracking and vice versa. The performances of the RL agents are compared with a classical PD controller. The results show that RL can perform quite well without the requirement of designing different controllers for each task if the system's dynamics is learned well.
dc.identifier.doi10.1017/S0263574722000273
dc.identifier.endpage3395
dc.identifier.issn0263-5747
dc.identifier.issn1469-8668
dc.identifier.issue10
dc.identifier.scopus2-s2.0-85127032141
dc.identifier.scopusqualityQ1
dc.identifier.startpage3378
dc.identifier.urihttps://doi.org/10.1017/S0263574722000273
dc.identifier.urihttps://hdl.handle.net/20.500.13099/1926
dc.identifier.volume40
dc.identifier.wosWOS:000770149600001
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherCambridge Univ Press
dc.relation.ispartofRobotica
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_WOS_20250316
dc.subjectcable-driven parallel robot
dc.subjectreinforcement learning
dc.subjectposition control
dc.subjecttorque distribution
dc.subjectMIMO system
dc.titlePosition control of a planar cable-driven parallel robot using reinforcement learning
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu